/explore
|
You are here 
|
www.greaterwrong.com | ||
| | | | |
ordinaryideas.wordpress.com
This post outlines a formalization of what Nick Bostrom calls "indirect normativity." I don't think it's an adequate solution to the AI control problem; but to my knowledge it was the first precise specification of a goal that meets the "not terrible" bar, i.e. which does not obviously lead to terrible consequences if pursued without... |
|
| | | | | ||
| | | | |
distill.pub
If we want to train AI to do what humans want, we need to study humans. |
|
| | | | | ||
| | | | |
www.alignmentforum.org
Nate Soares reviews a dozen plans and proposals for making AI go well. He finds that almost none of them grapple with what he considers the core prob... |
|
| | | | | ||
| | | | |
www.greaterwrong.com
In a recent tweet, Anthropic seems to have asserted that hyperstitionis responsible for observed misalignment in their AIs. Strangely, the research post they use as evidence appears to be only vaguely related to hyperstition[1]? I think this is part of a pattern by Anthropic of promoting the theory of hyperstition- the idea that writing about misaligned AI helps bring misaligned AI into existence- without explicitly calling it that. However, the research post shared with this tweet doesn't seem to be about writing misaligned AI into existence. Instead they find that training the model on reasoning traces- generated by reflecting on its constitution while giving users ethical advice on difficult dilemmas- reduces misaligned behavior. This presumably works by ... |
|
| | | |||
